search

PRBonn / SHINE_mapping

🌟 SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations (ICRA 2023)
MIT License
447 stars 32 forks source link

pretrain model #36

Closed whwh747 closed 3 months ago

whwh747 commented 3 months ago

Excellent work! Why does incremental reconstruction require loading a pre-trained model?

StarryN commented 3 months ago

Hello @whwh747. The goal is to minimize the impact of catastrophic forgetting on the results. You may check #29 and #19 for more details.